© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12358
    Prev
    Next
    INDEX
    Explanations

    Terminal application server

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĩįåıł
    -0.07
     overlap
    -0.07
    ä½ıæĪ¿åŁİ乡建设
    -0.07
    oves
    -0.06
    å§Ķ
    -0.06
    åľ¨åľ°ä¸Ĭ
    -0.06
    illo
    -0.06
    overlap
    -0.06
    åĨľä¸ļéĥ¨
    -0.06
    rik
    -0.06
    POSITIVE LOGITS
    çļĻ
    0.08
    OMIC
    0.08
    æľºæ¢°åĪ¶éĢłæľīéĻIJåħ¬åı¸
    0.07
    Lite
    0.07
    åĺĺ
    0.07
    æ¯Ķå¦Ĥåľ¨
    0.07
    USH
    0.07
    edException
    0.07
    DEL
    0.07
    usch
    0.07
    Activations Density 0.001%

    No Known Activations